Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pip
    -0.07
    (dirname
    -0.07
     місці
    -0.07
    illusion
    -0.07
     امنیت
    -0.07
     predictions
    -0.06
    лися
    -0.06
     perennial
    -0.06
    iage
    -0.06
     Нав
    -0.06
    POSITIVE LOGITS
    Rules
    0.07
     plais
    0.07
    副
    0.06
    戴
    0.06
     RedirectToAction
    0.06
     Mario
    0.06
     ödem
    0.06
     pdo
    0.06
    (requestCode
    0.06
     glEnd
    0.06
    Act Density 0.028%

    No Known Activations